Cisco Blogs

Cisco Blog > Data Center and Cloud

Cisco UCS Integrated Infrastructure for Big Data with Splunk Enterprise

The Cisco UCS Integrated Infrastructure for Big Data is the third generation of Cisco UCS Common Platform Architecture (CPA) for Big Data with significant improvements in performance and capacity. The solution has been widely adopted across major sectors including agriculture, education, entertainment, finance, healthcare, manufacturing and governments.

Today I’m pleased to announce that we are expanding our Cisco Integrated Infrastructure for Big Data portfolio to include joint reference architectures with Splunk. Splunk helps organizations unlock the value hidden within massive volumes of machine data generated by websites, applications, servers, networks, mobile devices and all the sensors and RFID assets that produce data every second of every day. Many organizations rely on Splunk for real-time end-to-end operational visibility and security intelligence, and as a result index terabytes of data every day across physical, virtual and cloud environments. A high performance, highly scalable, enterprise class infrastructure is critical.

Cisco has worked closely with Splunk to deliver a comprehensive solution with Splunk Enterprise that supports the massive scalability Splunk Enterprise deployments demand while delivering exceptional performance that dramatically exceeds Splunk reference hardware. See table 1. In short: Deploying Splunk Enterprise on UCS-based architectures enables organizations to improve performance up to 25x or index more than a TB/day with a 1 year retention policy.

Optimized for high performance or high data retention the solution is available in single instance (ideal for small-medium deployments) and scale-out cluster (designed for large scale deployments with data replication for redundancy).

High performance option: The single instance solution is based on UCS C220 M4 Server supports up to 250 GB* of indexing capacity per day with 1-month* data retention. The scale-out cluster solution consists of sixteen UCS C220 M4 Server (indexers), five UCS 220 M4 Servers (three search heads, two administration and master nodes) supports up to 8TB* of indexing capacity per day with a 16 day* data retention. Ideal for security, operations, and business intelligence use cases that require extremely fast response times for multiple concurrent searches.

High data retention option: The single instance solution is based on UCS C240 M4 Server supporting a 1 year retention period at 80GB per day Indexing capacity. The scale-out cluster consists of sixteen UCS C240 M4 Server (indexers), five UCS 220 M4 Servers (three search heads, two administration and master nodes) with a 1 year retention period at 1.25TB per day Indexing capacity. This solution is ideal for applications requiring a balance of performance with a long data retention period.

Table 1: Performance benchmark data on Cisco UCS High Retention Single Instance Architecture

Searching (No indexing load) – Average Searches Per Minute (4-64)
Search Type

Cisco UCS High Retention Single Instance Architecture

Performance Gains relative to Splunk Reference HW**

Dense Searches(1 in every 100 events)


2.13 x

Rare Searches(1 in every 1M events)


25.5 x

Very Rare Searches(1 in every 100M events)


16.8 x

Searching and Indexing -- Average Searches Per Minute (4-64)
Search Type

Cisco UCS High Retention Single Instance Architecture

Performance Gains Relative to Splunk Reference HW**

Dense Searches(1 in every 100 events)


1.1 x

Rare Searches(1 in every 1M events)


15 x

Very Rare Searches(1 in every 100M events)


9.6 x

Together, Cisco and Splunk are helping organizations break down internal silos and harness big data to deepen business and customer understanding, mitigate cybersecurity risk, prevent fraud, improve service performance and reduce cost.

* Indexing capacity and data retention are inversely related, and a smaller indexing volume enables a greater retention capacity.
** Based on reference hardware specs outlined in the Splunk Capacity Planning Manual.

Additional Information
Cisco UCS Integrated Infrastructure for Big Data with Splunk Enterprise


Nimble Storage extends Adaptive Flash Platform with 16G FC, more deployment options

As customers continue to look for points of differentiation in their markets, the Storage Area Network (SAN) continues to play a vital role in enabling businesses to adopt new technologies and applications to help them grow.  To provide the highest reliability, scalability, and performance, organizations have traditionally deployed Fibre Channel (FC) storage networks and many will continue to do so.   FC is still a  preferred choice for enterprises (large and small), and the market transition from 4/8 G to 16 G is the best proof that the FC market is still strong.   Ethernet-based Storage solutions are also gaining mindshare and some of our customers desiring a unified data center fabric use Ethernet-based Storage protocols to reap the benefit of convergence.

We are sometimes asked about how Cisco MDS products will support the latest generation of storage technology on the market, namely flash.   Industry influencers have asked us if SAN technology will continue to be relevant as these newer memory technologies gain market share.  Can SAN technology cope with the increased performance and workload consolidation enabled by flash-based arrays?

Our answer is a resounding “Yes”: SAN solutions are here to stay.  No matter the underlying storage components, it is still very important for customers to be able to manage enterprise-level storage requirements centrally, and to optimize storage delivery.   Cisco is committed to working with third-parties to ensure that our MDS SAN technology interoperates with leading edge storage technology, and we have certification programs in place to ensure smooth deployments for customers.

The most recent example of this industry collaboration is with Nimble. To support varying storage requirements, Nimble on Nov 18th announced its support for FC SAN on their Adaptive Flash platform; now customers have the choice of  iSCSI Ethernet-based storage or FC. Unique application requirements lead to application specific infrastructure needs and Cisco, along with Nimble, provide over 450 joint customers with differentiated solutions tailored to address customer needs.

Highlights of  announcement

  1. Nimble CS300, CS500 and CS700 series arrays offer both iSCSI and FC protocol support
  2. Nimble completed a beta program with more than 40 enterprises; Customers have purchased and deployed FC arrays in production environments.
  3. Introduced  expanded capacity providing ability to scale non-disruptively up to 1.5 PB of raw capacity and up to 128TB of flash per cluster

Read More »

Tags: , , ,

Take Out the Stress of Choosing the Right Cloud Provider

For many organizations, buying cloud services can be stressful. After all, as your business moves more and more into the cloud, you need to know your services and cloud provider are as reliable or better than if these services originated from within your own data center.

Buying cloud services can feel a lot like buying a car. How many of us really know what’s going on under the hood? We look at a few key stats like gas mileage and drive it around the block. Yeah, it accelerates and brakes. We know we’re safe and going to get relatively good gas efficiency. After all, cars have to meet certain standards. So in the end the decision comes down to price and comfort features such as how much we like the center console and cup holder.

But not all clouds are created equal. Low pricing and a fancy user portal are nice, but they aren’t what keep your business growing. Is best-effort service good enough for your operations? Can your organization afford to experience down time? Does your provider offer the flexibility you could get from other providers? Is your service truly enterprise-class?

The good news is that, just like there are standards in the car industry, there are standards for cloud. Services that are Cisco Powered, for example, have to meet strict requirements to carry the Cisco Powered logo. These requirements include certification and a third-party audit of every service to verify they deliver as promised.

You can learn more about what it takes to have confidence in your cloud provider from our partner, OneNeck. In their recent blog, “How to Reliably Offload IT Management to the Cloud,” they share a comprehensive list of factors to consider when choosing a cloud provider.
Selecting the right cloud provider and services doesn’t have to be frustrating and arbitrary. By understanding what comprises a reliable cloud, you can ask the right questions to ensure your provider is the best partner for your business.

Tags: , , ,

Discover the latest advances in Fibre Channel over Ethernet (FCoE) technology.

IT managers are finding it increasingly challenging to deliver the services end users demand while keeping operating costs under control.  A truly converged environment, using Fibre Channel over Ethernet (FCoE) to combine LAN and SAN architectures, can substantially reduce operating costs and simplify management while providing increased performance now and in the future.

How do you migrate to a converged solution without disrupting your existing data center architecture and IT investmentsRegister for this Webinar to Learn more: Dec 2nd *8:00 PST

Register Now

This live, 60-minute webcast will explore the latest advances in FCoE technology, including multihop and dynamic FCoE. You will learn how these and other recent innovations make the benefits of migrating to a converged network more realistic and compelling than ever before.

Read More »

Going Native with OpenStack Centric Applications: Overview

November 16, 2014 at 10:08 pm PST

OpenStack ApplicationsCloud infrastructure is useless without applications running atop, providing business services and solving customer needs. So, as applications ascend to the throne as the rightful king of cloud, focus sharpens on their support within OpenStack-based Cisco Intercloud. With this focus, let’s walk through a survey of components and projects supporting applications in OpenStack, understanding what a day in the life of an application in OpenStack is like. We’ll start with an overview of the application ecosystem comprised of a number of supporting projects. In the ecosystem overview below, relevant OpenStack projects are presented in context of existing, similar technologies with which you may be familiar. These similar technologies both under and overlap functionality of the respective OpenStack project, but are shown to hasten your general understanding of which bucket these projects fall into by way of tech you may already know (so, add a pinch of salt when considering relevancy of suggested affiliated technologies). Read More »

Tags: , ,